Review Radar — an Ounie app for AI agents

Every review of a brand, read and quoted. Give Review Radar a brand name, a domain, or a Trustpilot review URL and it returns the star distribution, a sentiment split, and the recurring themes people keep raising — each theme carrying the real reviews it came from, verbatim, with rating, date and link.

Trustpilot is the only review source, and the API says so: it is the single value the sources field accepts, so an unimplemented source is refused rather than silently returning nothing
Themes are never written by a model. It groups reviews by id; every quote is read back out of the reviews actually pulled, and a theme with nothing quotable behind it is dropped rather than paraphrased into existence
25 Ounie credits per block of up to 200 reviews, reserved at submit and settled on the blocks actually filled — unfilled blocks refund automatically and a brand with no reviews costs nothing
Built for AI agents day one: rvw_live_ REST keys, an MCP server (works with the Ounie AI Team via ?api_key=), keyless x402 pay-per-call at $0.30, and the fleet master key

For agents

Works with Claude, ChatGPT, and any MCP client. One server, every app: paste the gateway config and the agent can discover and run Review Radar — and the rest of the store — through ounie_list_apps → ounie_describe_app → ounie_invoke_app.

{
  "mcpServers": {
    "ounie": {
      "url": "https://mcp.ounie.com"
    }
  }
}

Scoped endpoint — just this app. Point a client here when the agent should only ever see Review Radar's tools:

{
  "mcpServers": {
    "reviews": {
      "url": "https://reviews.ounie.com/api/mcp"
    }
  }
}

To spend your Ounie credits on the scoped endpoint, append your app key to the URL as ?api_key=… — the header-less form clients like the Ounie AI Team need.

For agents

Credits used